“Preliminary analysis of the sentiment of news items covering scientific articles about COVID-19”
In a recent blog post, my co-authors Bijan Ranjbar-Sahraei, a freelance data scientist, Rodrigo Costas, senior researcher at the Centre for Science and Technology Studies (CWTS) at Leiden University, and I discuss the impact of COVID-19 research on the news by applying state-of-the-art sentiment analysis.
We use an existing dataset of scientific publications selected by the WHO/Dimensions and explore the potential of natural language processing (NLP), which incorporates sentiment analysis as an important indicator of expression of news media sentiment, to study some characteristics of the ‘infodemic’ related to the COVID-19 pandemic.
Recent shift towards neutrality
Overall, we see a slight increase in news neutrality as it shifts from a slightly negative sentiment in the early months to a more neutral sentiment.
Medical news sources are more neutral, while general and business-related outlets publish more negative news about COVID-19 related research.
Our blog post is a preliminary analysis of the sentiment of news items covering scientific articles about COVID-19 and it is by no means in its final stages. Nevertheless, it already reveals interesting findings worth sharing. It also shows the potential of machine learning models, such as text classification, to further study and characterize the online and social media reception of research objects.
The full version of our blog post can be found here:
S. Mahtani-Williams, W. Fulton, A. Desvars-Larrive, et al.
Landscape Genomics of a Widely Distributed Snake, Dolichophis caspius (Gmelin, 1789) across Eastern Europe and Western Asia
Genes 11(10) (2020) 1218
A. Chakraborty, Y. Ikeda
Testing “efficient supply chain propositions” using topological characterization of the global supply chain network
PLoS ONE 15(10) (2020) e0239669
J. Lasser, (...) J. Sorger
Complexity, transparency and time pressure: practical insights into science communication in times of crisis
Journal of Science Communication 19(05) (2020) N01